Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    specific song titles and prominent lyrical elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    unified methods, inferred causation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Lingkungan
    -0.50
     extranjera
    -0.45
     Könige
    -0.41
     Gegenteil
    -0.41
     directos
    -0.41
     ordinaire
    -0.40
     murni
    -0.40
    endientes
    -0.40
     Beiträge
    -0.40
     recuer
    -0.40
    POSITIVE LOGITS
     betweenstory
    1.04
    ]=>
    0.88
     otomatig
    0.87
    Tembelea
    0.86
     Numerade
    0.84
     Italijanski
    0.77
    parsedMessage
    0.74
    VIAF
    0.71
     surla
    0.71
    delwed
    0.70
    Act Density 0.041%

    No Known Activations